Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Occupational Exposure

    np_acts-logits-general · gemini-2.5-flash-lite

    text formatted in a specific way, particularly titles, headings, or formatted excerpts from books, articles, and publications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     Fußballspieler
    -1.64
    וּ
    -1.56
     compliqué
    -1.41
     бампер
    -1.40
    种类
    -1.38
     ciebie
    -1.38
    我没有
    -1.33
    尋找
    -1.31
    让我
    -1.30
     pequeñas
    -1.25
    POSITIVE LOGITS
     your
    2.14
     you
    1.63
     Administração
    1.45
     entidade
    1.42
     frambo
    1.41
     YOUR
    1.40
     sirup
    1.40
     chicco
    1.35
     dortmund
    1.34
    합니다
    1.33
    Act Density 0.005%

    No Known Activations